Rohith Krishna
@r_krishna3
@UWproteindesign
RFdiffusion2 generates new enzyme structures just from the most basic descriptions of their geometry. See @woodyahern's thread to see the next generation of de novo enzyme design:
New enzymes can unlock chemistry we never had access to before. Here, we introduce RFdiffusion2 (RFD2), a generative model that makes significant strides in de novo enzyme design. Preprint: biorxiv.org/content/10.110… Code: coming soon Animation credit: x.com/ichaydon (1/n)
Excited to see this out! congrats @DaveJuergens and team :)
Late, but got it done. Inference and training code for CA RFDiffusion is available here: github.com/baker-laborato… Please have fun. Getting this online was an adventure, to say the least.
RFdiffusion => generative binder design. RFdiffusion2 => generative enzyme design. It's rare to find scientists with deep knowledge in chemistry, machine learning, and software engineering like Woody. The complexity of enzymes matches the complexity of his skills. Check out RFD2
New enzymes can unlock chemistry we never had access to before. Here, we introduce RFdiffusion2 (RFD2), a generative model that makes significant strides in de novo enzyme design. Preprint: biorxiv.org/content/10.110… Code: coming soon Animation credit: x.com/ichaydon (1/n)
Congrats Joe and team!
I’m excited to share our significantly-updated preprint on de novo antibody design, where we now demonstrate the structurally accurate design of scFvs (in addition to VHHs) with RFdiffusion! biorxiv.org/content/10.110…
Anna and Sam figured out subtle geometric details of serine hydrolase active sites, and then figured out how make new proteins which fold up to reconstruct those active sites with sub-angstrom accuracy and catalyze ester hydrolysis. They are absolutely savage and inspiring.
New research in Science represents a notable step forward in designing enzymes from scratch. With a new approach, researchers designed an enzyme that uses a covalent intermediate to catalyze a two-step reaction, analogous to what many proteases do when breaking apart proteins.…
How can a single cell learn without a brain or nervous system? We explore this in my new preprint with @WallaceUcsf! We discovered that central features of learning in single cells can be accounted for by a model based on receptor inactivation bit.ly/3CDukfS 🧵 1/n
🧵(1/7) Excited to share that our work, EquiformerV2, has been accepted to #ICLR2024. EquiformerV2 is the state-of-the-art on large-scale atomistic benchmarks -- OC20, OC22, AdsorbML, and ODAC23. Joint work with @bwood_m, @abhshkdz from @OpenCatalyst and @tesssmidt Paper:…
Our work on modeling and designing biomolecular assemblies is now in @ScienceMagazine. science.org/doi/10.1126/sc… RFAA Code: github.com/baker-laborato… RFdiffusionAA Code: github.com/baker-laborato…
🎉 Excited to share that our paper "De novo design of high-affinity binders of bioactive helical peptides" is officially out! nature.com/articles/s4158… Hats off to coauthors @definitelyphil and @PreethamVi for making this project a reality. 🙌 Grateful for their collaboration!
Excited to share a new preprint we just released on the de novo design of allosterically controllable protein assemblies biorxiv.org/content/10.110…
RFdiffusionAA generating a small molecule binding protein against an experimental FXIa inhibitor (OQO), a ligand which is significantly different than any in its training dataset.
Very excited to share RoseTTAFold All-Atom and RFdiffusion All-Atom, methods for structure prediction and design of biomolecular assemblies! biorxiv.org/content/10.110… 1/n
RoseTTAFold updated to be All-Atom... biological assemblies containing proteins, nucleic acids, small molecules, metals, and covalent modifications ... and diffusion🤯biorxiv.org/content/10.110…
Sharing an early preprint of my Microsoft AI4Science summer internship project. We developed SE(3) flow matching for protein backbone generation. Compared to SE(3) diffusion, we find our method achieves higher designability, faster sampling, with a way simpler implementation. 1/8